Redundancy removal feature selection method LLRFC score+ based on LLRFC and correlation analysis
A feature selection method and correlation analysis technology, applied in the field of tumor classification research in bioinformatics, can solve problems such as poor interpretation, no consideration of the relationship between feature genes, and no clear biological significance, and achieve computational time complexity The effect of high and high experimental cost
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment
[0040] Eleven different tumor data sets (11Tumors) on the website http: / / www.gems-system.org are used for classification verification, and feature selection methods such as LLRFCscore+, LLRFCscore, Laplacianscore, Fisherscore, t-test, etc. are compared here The classification accuracy rate on the data set and the characteristics of the data set are listed in the following table:
[0041] Table 111Tumors
[0042] Number of genes: 12533
[0043]
[0044]
[0045] Considering the balance of the tumor sample distribution, the data is randomly divided into equal parts by category, half of which is the training set, used for feature selection; the other half is the test set, used to test the classification accuracy and obtain the classification accuracy. Since SVM is not sensitive to data dimensionality, it shows great advantages in solving small sample high-dimensional problems. For gene expression profile data, the classifier uses LIBSVM, linear kernel function, and default parameters....
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com